Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    included notes or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оценка
    0.61
     평가
    0.50
     evaluates
    0.49
    Glare
    0.48
     оцен
    0.48
     оцени
    0.48
     оці
    0.48
    評
    0.48
     assesses
    0.46
    த்தோ
    0.46
    POSITIVE LOGITS
     sections
    0.70
     Notes
    0.67
     notes
    0.66
     portions
    0.66
     placeholders
    0.64
     customizable
    0.63
     instructions
    0.63
     placeholder
    0.63
    notes
    0.63
     optional
    0.60
    Act Density 0.008%

    No Known Activations